CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
Generate Ralph-compatible prompts for multiple related tasks.
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-task --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .claude/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .claude/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-taskType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-task --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .agents/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .agents/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-task --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .cursor/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .cursor/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/majiayu000/claude-skill-registry.git --path skills/ai-llm/ralph-prompt-multi-task--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-task --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .gemini/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .gemini/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-taskInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .github/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .github/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install majiayu000/claude-skill-registry ralph-prompt-multi-task --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-llm/ralph-prompt-multi-task .opencode/skills/ralph-prompt-multi-task && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ralph-prompt-multi-task" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/ralph-prompt-multi-task into .opencode/skills/ralph-prompt-multi-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ralph-prompt-multi-task", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ralph-prompt-multi-taskGenerate Ralph-compatible prompts for multiple related tasks.
Ralph Prompt Multi Task is an agent skill from majiayu000/claude-skill-registry. Generate Ralph-compatible prompts for multiple related tasks. Creates phased prompts with sequential milestones, cumulative progress tracking, and phase-based completion promises. Use when creating prompts for CRUD implementations, multi-step features, staged migrations, or any work requiring multiple distinct but related tasks.
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).
It sits in Product & Project Management, covering Project management. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 000116a. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlnpmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use curl and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ralph Prompt Multi Task loads about 3.9k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 621 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from majiayu000/claude-skill-registry at commit 000116a, republished under its MIT licence (© majiayu000). 621 words, ~3,923 tokens.
.claude/skills/ralph-prompt-multi-task/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Generates structured prompts for multiple related tasks that need to be completed in sequence or parallel. Uses phase-based organization with milestone tracking, cumulative success criteria, and clear progression through tasks.
Best For:
Ralph Philosophy: This generator embraces the principle that failures are deterministic and fixable. Each phase iteration learns from previous attempts. Don't fear failures—they're expected and provide data for improvement through prompt tuning.
Input Required:
Generate prompt with:
Generate a Ralph multi-task prompt for:
Tasks:
1. [Task 1]
2. [Task 2]
3. [Task 3]
Dependencies: [Task 2 depends on Task 1, etc.]
Final promise: [COMPLETION_PHRASE]Create a task inventory:
| Task # | Task Name | Dependencies | Verification | Est. Complexity |
|---|---|---|---|---|
| 1 | [Name] | None | [How to verify] | Low/Med/High |
| 2 | [Name] | Task 1 | [How to verify] | Low/Med/High |
| 3 | [Name] | Task 1 | [How to verify] | Low/Med/High |
| 4 | [Name] | Tasks 2, 3 | [How to verify] | Low/Med/High |
Group tasks into logical phases:
Phase Structure:
Each phase needs:
Use this template:
# Multi-Task: [Overall Objective]
## Overview
[1-2 sentences describing the overall goal and scope]
## Task Inventory
| # | Task | Phase | Dependencies | Verification |
|---|------|-------|--------------|--------------|
| 1 | [Task 1] | 1 | None | [Verification] |
| 2 | [Task 2] | 2 | Task 1 | [Verification] |
| 3 | [Task 3] | 2 | Task 1 | [Verification] |
| 4 | [Task 4] | 3 | Tasks 2, 3 | [Verification] |
## Phase 1: [Phase Name] (Foundation)
### Objective
[What this phase accomplishes]
### Tasks
1. **[Task 1 Name]**
- Requirements: [Specific requirements]
- Files: [Files to create/modify]
- Verification: [How to verify]
### Phase 1 Success Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] Tests pass: `[test command]`
### Phase 1 Checkpoint
When Phase 1 criteria met, document:PHASE 1 COMPLETE:
Continue to Phase 2.
---
## Phase 2: [Phase Name] (Core)
### Objective
[What this phase accomplishes]
### Prerequisites
- Phase 1 complete
- [Any specific requirements]
### Tasks
2. **[Task 2 Name]**
- Requirements: [Specific requirements]
- Files: [Files to create/modify]
- Verification: [How to verify]
3. **[Task 3 Name]**
- Requirements: [Specific requirements]
- Files: [Files to create/modify]
- Verification: [How to verify]
### Phase 2 Success Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] [Criterion 3]
- [ ] Tests pass: `[test command]`
### Phase 2 Checkpoint
When Phase 2 criteria met, document:PHASE 2 COMPLETE:
Continue to Phase 3.
---
## Phase 3: [Phase Name] (Enhancement/Validation)
### Objective
[What this phase accomplishes]
### Prerequisites
- Phases 1-2 complete
- [Any specific requirements]
### Tasks
4. **[Task 4 Name]**
- Requirements: [Specific requirements]
- Files: [Files to create/modify]
- Verification: [How to verify]
### Phase 3 Success Criteria
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] All tests pass: `[test command]`
---
## Final Verification
Run complete verification:
```bash
# All tests
[full test command]
# Integration check
[integration verification]
# Lint/Type check
[lint command]When ALL phases complete and all checklist items verified:
Output: <promise>[COMPLETION_PHRASE]</promise>
As you work, track progress in this format:
PROGRESS:
Phase 1: [COMPLETE/IN PROGRESS] - [X/Y tasks]
Phase 2: [COMPLETE/IN PROGRESS/NOT STARTED] - [X/Y tasks]
Phase 3: [COMPLETE/IN PROGRESS/NOT STARTED] - [X/Y tasks]
Overall: [X/Y tasks complete]
## Example Prompts
### Example 1: CRUD API Implementation
**Input:**
- Tasks: Create, Read (single), Read (list), Update, Delete for Products
- Dependencies: Create first, then others can be parallel
- Promise: CRUD_API_COMPLETE
**Generated Prompt:**
```markdown
# Multi-Task: Product CRUD API Implementation
## Overview
Implement complete CRUD operations for Products resource with RESTful endpoints, validation, and comprehensive tests.
## Task Inventory
| # | Task | Phase | Dependencies | Verification |
|---|------|-------|--------------|--------------|
| 1 | Product model/schema | 1 | None | Model exists, validates |
| 2 | POST /products (Create) | 2 | Task 1 | Returns 201, creates record |
| 3 | GET /products/:id (Read) | 2 | Task 1 | Returns 200, correct data |
| 4 | GET /products (List) | 2 | Task 1 | Returns array, pagination |
| 5 | PUT /products/:id (Update) | 3 | Tasks 2,3 | Returns 200, updates record |
| 6 | DELETE /products/:id | 3 | Tasks 2,3 | Returns 204, removes record |
| 7 | Integration tests | 4 | Tasks 2-6 | All scenarios pass |
## Phase 1: Foundation
### Objective
Create Product model with validation and database schema.
### Tasks
1. **Product Model**
- Requirements:
- Fields: id, name, description, price, category, createdAt, updatedAt
- Validation: name required, price > 0, category from enum
- Files: `src/models/product.ts`, `src/schemas/product.ts`
- Verification: Model compiles, validation tests pass
### Phase 1 Success Criteria
- [ ] Product model created with all fields
- [ ] Validation rules implemented
- [ ] Database migration/schema created
- [ ] Model tests pass: `npm test -- --grep "Product model"`
### Phase 1 CheckpointPHASE 1 COMPLETE:
---
## Phase 2: Core CRUD Operations
### Objective
Implement Create, Read (single), and Read (list) endpoints.
### Prerequisites
- Phase 1 complete (Product model exists)
### Tasks
2. **POST /products (Create)**
- Requirements:
- Accept JSON body with product data
- Validate input using schema
- Return 201 with created product
- Return 400 for validation errors
- Files: `src/routes/products.ts`, `src/controllers/products.ts`
- Verification: `curl -X POST -H "Content-Type: application/json" -d '{"name":"Test","price":9.99,"category":"electronics"}' localhost:3000/products`
3. **GET /products/:id (Read Single)**
- Requirements:
- Return 200 with product data
- Return 404 if not found
- Files: `src/routes/products.ts`, `src/controllers/products.ts`
- Verification: `curl localhost:3000/products/1`
4. **GET /products (List)**
- Requirements:
- Return array of products
- Support pagination: page, limit query params
- Return metadata: total, page, limit, totalPages
- Files: `src/routes/products.ts`, `src/controllers/products.ts`
- Verification: `curl "localhost:3000/products?page=1&limit=10"`
### Phase 2 Success Criteria
- [ ] POST /products creates product, returns 201
- [ ] POST /products returns 400 for invalid data
- [ ] GET /products/:id returns product
- [ ] GET /products/:id returns 404 for missing
- [ ] GET /products returns paginated list
- [ ] All endpoint tests pass: `npm test -- --grep "products"`
### Phase 2 CheckpointPHASE 2 COMPLETE:
---
## Phase 3: Update and Delete Operations
### Objective
Complete CRUD with Update and Delete endpoints.
### Prerequisites
- Phase 2 complete (Create and Read working)
### Tasks
5. **PUT /products/:id (Update)**
- Requirements:
- Accept JSON body with update data
- Partial updates allowed
- Return 200 with updated product
- Return 404 if not found
- Return 400 for validation errors
- Verification: `curl -X PUT -H "Content-Type: application/json" -d '{"price":19.99}' localhost:3000/products/1`
6. **DELETE /products/:id**
- Requirements:
- Return 204 on success (no content)
- Return 404 if not found
- Actually remove record from database
- Verification: `curl -X DELETE localhost:3000/products/1`
### Phase 3 Success Criteria
- [ ] PUT /products/:id updates product
- [ ] PUT returns 404 for missing, 400 for invalid
- [ ] DELETE /products/:id removes product
- [ ] DELETE returns 404 for missing
- [ ] All endpoint tests pass
### Phase 3 CheckpointPHASE 3 COMPLETE:
---
## Phase 4: Integration & Validation
### Objective
Complete test coverage and integration verification.
### Tasks
7. **Integration Tests**
- Requirements:
- Full CRUD flow test (create, read, update, delete)
- Error handling tests (400, 404 scenarios)
- Pagination tests
- Edge cases (empty database, special characters)
- Files: `tests/integration/products.test.ts`
### Phase 4 Success Criteria
- [ ] Integration tests cover full CRUD flow
- [ ] Error scenarios tested
- [ ] All tests passing: `npm test`
- [ ] No TypeScript errors: `npm run typecheck`
---
## Final Verification
```bash
# All tests
npm test
# Type check
npm run typecheck
# Manual CRUD flow test
curl -X POST -H "Content-Type: application/json" -d '{"name":"Test Product","price":29.99,"category":"electronics"}' localhost:3000/products
curl localhost:3000/products
curl localhost:3000/products/1
curl -X PUT -H "Content-Type: application/json" -d '{"price":39.99}' localhost:3000/products/1
curl -X DELETE localhost:3000/products/1When ALL phases complete and all checklist items verified:
Output: <promise>CRUD_API_COMPLETE</promise>
PROGRESS:
Phase 1: [status] - 1/1 tasks
Phase 2: [status] - 3/3 tasks
Phase 3: [status] - 2/2 tasks
Phase 4: [status] - 1/1 tasks
Overall: X/7 tasks complete
### Example 2: CI/CD Pipeline Setup
**Input:**
- Tasks: Lint, Test, Build, Deploy staging, Deploy prod
- Dependencies: Sequential progression
- Promise: PIPELINE_COMPLETE
**Generated Prompt:**
```markdown
# Multi-Task: CI/CD Pipeline Implementation
## Overview
Set up complete CI/CD pipeline with linting, testing, building, and staged deployments using GitHub Actions.
## Task Inventory
| # | Task | Phase | Dependencies | Verification |
|---|------|-------|--------------|--------------|
| 1 | Workflow file structure | 1 | None | File exists |
| 2 | Lint job | 2 | Task 1 | Workflow runs lint |
| 3 | Test job | 2 | Task 2 | Tests run in CI |
| 4 | Build job | 3 | Task 3 | Build artifacts created |
| 5 | Deploy staging | 4 | Task 4 | Staging deployment works |
| 6 | Deploy production | 4 | Task 5 | Prod deployment works |
## Phase 1: Workflow Foundation
### Tasks
1. **Workflow File Structure**
- Create `.github/workflows/ci.yml`
- Define triggers (push to main, PRs)
- Set up job structure
### Phase 1 Success Criteria
- [ ] Workflow file exists and is valid YAML
- [ ] Triggers defined for push and PR
---
## Phase 2: Quality Gates
### Tasks
2. **Lint Job**
- Run linter on all source files
- Fail pipeline if lint errors
3. **Test Job**
- Depends on lint passing
- Run full test suite
- Upload coverage report
### Phase 2 Success Criteria
- [ ] Lint job runs and catches errors
- [ ] Test job runs full suite
- [ ] Pipeline fails if tests fail
---
## Phase 3: Build
### Tasks
4. **Build Job**
- Depends on tests passing
- Create production build
- Upload build artifacts
### Phase 3 Success Criteria
- [ ] Build creates production artifacts
- [ ] Artifacts uploaded and accessible
---
## Phase 4: Deployments
### Tasks
5. **Deploy Staging**
- Automatic on main branch
- Deploy to staging environment
6. **Deploy Production**
- Manual approval required
- Deploy to production
### Phase 4 Success Criteria
- [ ] Staging auto-deploys on main
- [ ] Production requires manual trigger
- [ ] Both environments update correctly
---
## Completion
When all phases verified:
Output: <promise>PIPELINE_COMPLETE</promise>/ralph-wiggum:ralph-loop "[paste generated prompt]" --completion-promise "YOUR_PROMISE" --max-iterations 50Recommended iterations by complexity:
--max-iterations 35-45--max-iterations 50-70--max-iterations 80-100For single-task prompts, see ralph-prompt-single-task.
For project-level prompts, see ralph-prompt-project.
For research/analysis prompts, see ralph-prompt-research.
© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/ai-llm/ralph-prompt-multi-task of majiayu000/claude-skill-registry.
Open the folder on GitHubat commit 000116a
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.
Ralph Prompt Multi Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ralph Prompt Multi Task this skillmajiayu000/claude-skill-registry | 666 | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Uvastral-sh/claude-code-plugins | 314 | 2 repos | ~980 | Automated safety check: Pass | Apache-2.0 | |
| Project Managementkunchenguid/firstmate | 7.6k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Hivemind Goalsactiveloopai/hivemind | 1.6k | — | ~1.7k | Automated safety check: Notes | Apache-2.0 | |
| Ichartjswanghetommy/ichartjs | 352 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 |
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
astral-sh/claude-code-plugins
Guide for using uv, the Python package and project manager. An agent skill from astral-sh/claude-code-plugins.
kunchenguid/firstmate
Agent-only procedure for Firstmate project management. An agent skill from kunchenguid/firstmate.
activeloopai/hivemind
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.
wanghetommy/ichartjs
Plan, validate, render, explain, and safely edit iChart.js visualizations from tabular, project, or diagram data.
activeloopai/hivemind
Create, track and update team goals in Hivemind via the hivemind CLI.
majiayu000/claude-skill-registry
Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.
majiayu000/claude-skill-registry
Neural search via Exa MCP for web, code, and company research.
majiayu000/claude-skill-registry
Unified media generation via fal.ai MCP — image, video, and audio.
majiayu000/claude-skill-registry
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.
majiayu000/claude-skill-registry
Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.
majiayu000/claude-skill-registry
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.
Categories
Generate Ralph-compatible prompts for multiple related tasks. Ralph Prompt Multi Task is an agent skill from majiayu000/claude-skill-registry. Generate Ralph-compatible prompts for multiple related tasks.
Ralph Prompt Multi Task fits situations like: creating prompts for CRUD implementations; multi-step features; staged migrations; any work requiring multiple distinct but related tasks.
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a claude-code`. Or copy the skill folder (skills/ai-llm/ralph-prompt-multi-task in majiayu000/claude-skill-registry) into .claude/skills/ralph-prompt-multi-task in your project. Claude Code loads it when a task matches its description.
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a codex`. Or copy the skill folder (skills/ai-llm/ralph-prompt-multi-task in majiayu000/claude-skill-registry) into .agents/skills/ralph-prompt-multi-task in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/claude-skill-registry --skill ralph-prompt-multi-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph-prompt-multi-task, .gemini/skills/ralph-prompt-multi-task, .github/skills/ralph-prompt-multi-task and .opencode/skills/ralph-prompt-multi-task in your project.
Going by SKILL.md and its folder, Ralph Prompt Multi Task needs the command-line tools its instructions call (curl and npm).
SKILL.md contains no URLs. Its commands use curl and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ralph Prompt Multi Task is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ralph Prompt Multi Task: CCPM Project Management (automazeio/ccpm, 8.4k stars), Uv (astral-sh/claude-code-plugins, 314 stars), Project Management (kunchenguid/firstmate, 7.6k stars) and Hivemind Goals (activeloopai/hivemind, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 971 skills in this directory. The repository was last updated on October 7, 2026.
Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.